Extended model architecture and loss fn to the newer paper.
Predictions on test image:
- Can detect object boundaries well, due to added image gradient component in the newer loss fn.
- Prediction quality is decent considering from single image
- Model produces depthmaps at lower resolution (320x240)
- Depthmaps lack clarity
- Model is really large, ~900MB, inference time is ~2s for a mini-batch of 8 (640x480) images
Model weights: https://oregonstate.box.com/s/p3lbkgiwufg9rxfgx53c4svnzz2lz9av
NYU Depth Datasets: https://cs.nyu.edu/~silberman/datasets/